GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

TL;DR

GEPA is a prompt optimization method that leverages natural language reflection, outperforming reinforcement learning and existing prompt optimizers in efficiency and accuracy across multiple tasks.

Contribution

Introduces GEPA, a natural language reflection-based prompt optimizer that surpasses RL and prior methods in efficiency and effectiveness for LLM task adaptation.

Findings

GEPA outperforms GRPO by 6% on average across six tasks.

GEPA uses up to 35x fewer rollouts than RL methods.

GEPA exceeds MIPROv2 performance by over 10% in accuracy.

Abstract

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa .